Split requirements: slim runtime for HF Space, dev file for full training stack

Fix HF Spaces YAML: valid colorFrom value, shorten short_description to <=60 chars

Merge branch 'codex/v2.5-support-navigator'

Tighten section spacing, remove HF deploy block, narrative scope, restore teammate credit

Tighten README: narrative scope section, remove HF-internal content, credit teammate in contributors

Merge branch 'codex/v2.5-support-navigator'

Polish scope, limitations, roadmap, docs sections for readability

Merge branch 'codex/v2.5-support-navigator'

Refine public README: cleaner narrative, named design iterations, neutral attribution

Bring V4 narrative README + HF Spaces config into main

Diversity probe sweep + V1->V4 narrative README + HF Spaces entry + DV/incomplete fixes

Bring response-quality fixes into main

Response quality: greeting/goodbye/meta handlers, slang routing, lexical variety, last-verified badge, markdown norm, crisis variants

Bring README rewrite into main

Rewrite public README: Mermaid flowchart, headline numbers up top, V1 vs V4 story

Integrate V3 listening + V4 plan-and-rephrase + V4.4 polish into main

Repo cleanup: tighten public README + remove internal docs from tracking

V4.4 Tier 3: refreshed full project audit + error analysis writeup

V4.4 Tier 2: safety-pipeline UI visualization, paper results section, demo script, mobile CSS, HIPAA + privacy docs

V4.4 Tier 1: regex hardening, clarify-stage enum, stat caveats, PDF unicode, retry/backoff, reproducibility doc

V4.3: prompt-injection audit, input length cap, per-layer ablation, unguarded baseline, limitations restored

V4.2 part 3: sycophancy guard, F-1 flag decay, incomplete-message handler

V4.2 part 2: authority-misconduct route + conversation history in rephraser

V4.2 part 1: fix broken ISSS URL, ship URL audit + Karthik data brief

V4.1: fix repetition/scroll/topbar, add PDF export, counselor-assist note

V4: streaming, controlled paraphrasing, support plan, voice, sweeps

Add LLM plan-and-rephrase layer with Groq + Anthropic providers

Add stage-aware listening planner and F-1 student awareness

Add full Opus project audit

Improve conversational MVP routing

Polish MVP support experience

Update Core project notes

Add Eval B safety supplement

Ingest Core dataset and harden router policy

Prepare Core dataset intake and resource registry

Add live demo decision console

Polish peer helper and scope handling

Add Core safety metadata and eval summaries

Lock checklist and Karthik dataset handoff

Organize project documentation

Document EmpathRAG Core merged plan

Implement EmpathRAG Core hybrid router

Add Karthik eval harness and safety patches

Start V2.5 support navigator hardening

Checkpoint V2 curated support navigator

Add curated corpus integration scaffold

Start v2 safety hardening

chore: harden .gitignore — data artifacts + session artifact patterns

chore: add .claude/ to .gitignore

docs: correct metric attribution and condition count